Artificial intelligence (AI) applications in healthcare and medicine have increased in recent years. To enable access to personal data, Trusted Research environments (TREs) provide safe and secure environments in which researchers can access sensitive personal data and develop Artificial Intelligence (AI) and Machine Learning models. However currently few TREs support the use of automated AI-based modelling using Machine Learning. Early attempts have been made in the literature to present and introduce privacy preserving machine learning from the design point of view [1]. However, there exists a gap in the practical decision-making guidance for TREs in handling models disclosure. Specifically, the use of machine learning creates a need to disclose new types of outputs from TREs, such as trained machine learning models. Although TREs have clear policies for the disclosure of statistical outputs, the extent to which trained models can leak personal training data once released is not well understood and guidelines do not exist within TREs for the safe disclosure of these models.
In this paper we introduce the challenge of disclosing trained machine learning models from TREs. We first give an overview of machine learning models in general and describe some of their applications in healthcare and medicine. We define the main vulnerabilities of trained machine learning models in general. We also describe the main factors affecting the vulnerabilities of disclosing machine learning models. This paper also provides insights and analyses methods that could be introduced within TREs to mitigate the risk of privacy breaches when disclosing trained models.
GRAIMATTER Green Paper: Recommendations for disclosure control of trained Machine Learning (ML) models from Trusted Research Environments (TREs)
TREs被广泛使用,并越来越多地用于支持跨一系列部门的敏感数据的统计分析(例如,卫生、警察、税务和教育),因为它们可以实现安全和透明的研究,同时保护数据机密性。学术界和工业界越来越希望在TREs中训练AI模型。人工智能领域正在快速发展,其应用包括发现人为错误,简化流程,任务自动化和决策支持。这些复杂的人工智能模型需要更多的信息来描述和复制,这增加了从这些描述中推断敏感个人数据的可能性。TREs没有针对这些风险的成熟流程和控制措施。这是一个复杂的话题,期望所有TRE都意识到所有风险,或者TRE研究人员已经在AI特定培训中解决了这些风险,这是不合理的。GRAIMATTER已经为TREs开发了一套可用的建议草案,以防范TREs在披露经过训练的AI模型时的额外风险。这些建议的制定得到了GRAIMATTER UKRI DARE UK sprint研究项目的资助。我们的建议的此版本于2022年9月项目结束时发布。在该项目的过程中,我们确定了许多领域,供今后进行调查,以便在实践中扩大和检验这些建议。因此,我们预计这份文件将随着时间的推移而发展。
Safe machine learning model release from Trusted Research Environments: The SACRO-ML package
School of Computer Science, University of the West of England(西英格兰大学计算机科学学院);School of Medicine, University of Dundee(邓迪大学医学院);Department of Mathematical Sciences, University of Durham(达勒姆大学数学科学系);Department of Physics, King’s College London(伦敦国王学院物理系);NHS National Services Scotland(苏格兰国家健康服务)
Resource-constrained Remote Attestation of Smart Meters Using Merkle Trees in a Trusted Execution Environment
Faculty of Electrical and Computer Engineering, Tarbiat Modares University(塔比巴特莫达雷斯大学电气与计算机工程学院);Fouman Faculty of Engineering, College of Engineering, University of Tehran(德黑兰大学工程学院福曼工程学院)